Application of the Mean-shift Segmentation Parameters Estimator (MSPE) to VHSR satellite images: Tetuan-Morocco

O. Benarchid, N. Raissouni, J.A. Sobrino, A. El Ayyan

Abstract

Image segmentation is considered as crucial step dealing with Object-Based Image Analysis (OBIA) and different segmentation results could be achieved by combining possible parameters values. Optimal parameters selection is usually carried out on the basis of visual interpretation; therefore, defining optimal combinations is a challenging task. In the present research, Mean-shift Segmentation Parameters estimator (MSPE) proposed tool is applied to automate the selection of segmentation parameters values to Very High Spatial Resolution (VHSR) satellite images in the region of Tetuan city (Northern Morocco). MSPE estimates the parameters values for the Mean-shift Segmentation (MS) algorithm. However, this algorithm needs as inputs: i) existing vector database and, ii) spectral data to define automatically the segmentation parameter values. Finally, application of the MSPE method on different landscape’ types show accurate results with Under-Segmentation (US) values ≤0.20 for industrial, residential and rural zones, while for dense residential area values of 0.35.


Keywords

MSPE; satellite; very high spatial resolution; Tetuan-Morocco

Full Text:

PDF

References

Blaschke, T. 2010. Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 65(1), 2-16. http://dx.doi.org/10.1016/j.isprsjprs.2009.06.004

Carleer, A., Deiber, O., Wolff, E. 2005. Assessment of very high spatial resolution satellite image segmentations. Photogrammetric Engineering and Remote Sensing, 71, 1285-1294.

Cheng, Y. 1995. Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(8), 790-799. http://dx.doi.org/10.1109/34.400568

Clinton, N., Holt, A., Scarborough, J., Yan, L., Gong, P. 2010. Accuracy assessment measures for object-based image segmentation goodness.

Photogrammetric Engineering and Remote Sensing, 76, 289-300.

Comaniciu, D., Meer, P. 2002. Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5), 603-619. http://dx.doi.org/10.1109/34.1000236

Drǎguţ, L., Tiede, D., Levick, S. R. 2010. ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed

data. International Journal of Geographical Information Science, 24(6), 859-871. http://dx.doi.org/10.1080/13658810903174803

Fukunaga, K., Hostetler, L. 1975. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions on Information Theory, 21(1), 32-40. http://dx.doi.org/10.1109/TIT.1975.1055330

Hanson, E., Wolff, E., 2010. Change detection for update of topographic databases through multi-level region-based classification of VHR optical and SAR data. In GEOBIA 2010: Geographic Object-Based Image Analysis, Ghent, Belgium, June 29-July 02.

Huth, J., Kuenzer, C., Wehrmann, T., Gebhardt, S., Tuan, V. Q., Dech. S. 2012. Land cover and land use classification with TWOPAC: towards automated processing for pixel- and object-based image classification. Remote Sensing, 4(9), 2530-2553. http://dx.doi.org/10.3390/rs4092530

Liu, Y., Bian, L., Meng, Y., Wang, H., Zhang, S., Yang, Y., Shao, X., Wang, B. 2012. Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis. ISPRS Journal of

Photogrammetry & Remote Sensing, 68, 144-156.

http://dx.doi.org/10.1016/j.isprsjprs.2012.01.007

Abstract Views

3414
Metrics Loading ...

Metrics powered by PLOS ALM




 

This journal is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International

Universitat Politècnica de València

Official Journal of the Spanish Association of Remote Sensing

e-ISSN: 1988-8740    ISSN: 1133-0953           https://doi.org/10.4995/raet